CivArchive
    GonzaLomo Krea 2 - v4.0
    NSFW
    Preview 140231415
    Preview 140160873
    Preview 140542723
    Preview 140160447
    Preview 140160018
    Preview 140160053
    Preview 140160052
    Preview 140159948
    Preview 140160055
    Preview 140160126
    Preview 140543064
    Preview 140160125
    Preview 140160444
    Preview 140160448
    Preview 140160740
    Preview 140537739
    Preview 140537871
    Preview 140537900
    Preview 140542700
    Preview 140542689

    Note: There are two FP8 download options for many versions. The 17GB option is an all-in-one checkpoint that includes the text encoder and vae as well, so load it like a regular checkpoint. The 12GB option is just the unet so load it like any diffusion model.

    So many new model architectures, I can't keep up. Krea 2 is definitely going to have a place in my toolbox though. It might be the best current T2I model.

    For best results, follow the recommended suggestions in the About This Version section. All of my images has an embedded ComfyUI workflow.

    • v1.0 seems to be very good at NSFW content but it has the problem of producing unprompted nudity.

    • v1.0 Alt has addressed the unprompted nudity issue to some extent but is weaker at NSFW.

    • v2.0 Training Base is my test bed for new training.

    • v2.0 RC1 is a potential release candidate that builds on Training Base.

    • v2.0 Final is based on the original v1.0, abandoning the ALT, Training Base and RC lineages completely.

    • v3.0 is just a refinement of v2.0.

    Beginning with v2.0, there are at least 5 versions available for download:

    • BF16

    • FP8

    • INT8 convrot

    • Q4_0 GGUF

    • FP8 All-in-One Checkpoint (text encoder and vae included)

    Description

    FAQ

    Checkpoint
    Krea 2
    by GBRX
    Download (Beta) View on CivitAI
    base model

    Details

    Downloads
    19,834
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/23/2026
    Updated
    11/11/2026
    Deleted
    -

    Files

    gonzaLomoKrea2_v40_fp8.safetensors

    Size:
    11.94 GB
    SHA256:
    e4385e1f347e78027dcb7f655dc4966a953bfe814a0257f81f5106fdf5e8680b

    Mirrors

    HuggingFace (4 mirrors)
    CivitAI (1 mirrors)

    gonzaLomoKrea2_v40_bf16-Q4_0.gguf

    Size:
    7.74 GB
    SHA256:
    8150317680be702c6d64110b367df2c93542bd62910ed56b750da6f37c579fd3

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    gonzaLomoKrea2_v40_Q8_0.gguf

    Size:
    13.56 GB
    SHA256:
    3a1ad8a69830124bb8a72bdbc11a1f72fc6d57f38d68f11cd15783a33cdcf6f4

    Mirrors

    CivitAI (1 mirrors)

    gonzaLomoKrea2_v40_fp8_AIO.safetensors

    Size:
    17.06 GB
    SHA256:
    b5e886b9acc32179e0ae7370d085b2a6f3607340d49e241b8853ddd004ea550b

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    qwen_image-vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (363 mirrors)
    CivitAI (310 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (7 mirrors)

    qwen3vl_4b_fp8_scaled.safetensors

    Size:
    4.88 GB
    SHA256:
    54bd5144df0bbc25dd6ccadfcb826b521445a1b06ae5a42570bdd2974ca87094

    Mirrors

    HuggingFace (104 mirrors)
    CivitAI (22 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (1 mirrors)

    gonzaLomoKrea2_v40_bf16.safetensors

    Size:
    23.88 GB
    SHA256:
    bc43fc509c590d2f79d5d45695c50f9d64f4c1f436f7c20925f765f5e784b45d

    Mirrors

    HuggingFace (3 mirrors)
    CivitAI (1 mirrors)

    gonzaLomoKrea2_v40_int8_convrot.safetensors

    Size:
    12.57 GB
    SHA256:
    fe60e264437d93cac026025738157d763d1f311b90a22afd56d1fe7497c36f9f

    Mirrors

    HuggingFace (3 mirrors)
    CivitAI (1 mirrors)

    gonzaLomoKrea2_v40_SVDQuant-W4A4.safetensors

    Size:
    7.31 GB
    SHA256:
    ca737cee31db37a1fb54bc00f16dfd9d25819537dd684dbab40e52610ecd562f

    Mirrors

    HuggingFace (4 mirrors)
    CivitAI (1 mirrors)